Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 322
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, tmax, tmin, precip, nevada, prof_nieve
• Dimensiones del mapa: 5,5
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-322.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.611.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
   7    3 7752 4058 7964 1346 5052 6330 9390 7115   70 5228 9265 2121 8103   21 
  17   18   19   20   21   22   23   24   25 
1808 1016 4436 5948    5  284 2405 5152    2 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "precip", "nevada", "prof_nieve")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

     fecha_cnt       tmax       tmin     precip       nevada  prof_nieve
[1,] 0.6798559  0.6798384  0.6279783 -0.4927985 -0.008608152 -0.06473787
[2,] 0.5119493 -0.5446353 -0.4930553  0.3241697 -0.001318159  0.03113376

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

    nevada prof_nieve       tmax  fecha_cnt       tmin     precip 
 0.9858829  0.9692657  0.9516994  0.9506053  0.9351547  0.9191379 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.:148.0   1st Qu.:  53.00   1st Qu.:  3.00  
 Median : 6.000   Median :198.0   Median :  98.00   Median : 10.00  
 Mean   : 6.497   Mean   :200.2   Mean   :  98.87   Mean   : 16.25  
 3rd Qu.: 9.000   3rd Qu.:255.0   3rd Qu.: 148.00   3rd Qu.: 22.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :422.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:38.28   1st Qu.: -5.6417  
 Median :0.0000000   Median :  0.0000   Median :40.82   Median : -3.4500  
 Mean   :0.0001897   Mean   :  0.3974   Mean   :39.66   Mean   : -3.4350  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.08   3rd Qu.:  0.4914  
 Max.   :3.0000000   Max.   :892.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  42.0  
 Median : 247.0  
 Mean   : 418.5  
 3rd Qu.: 656.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt        tmax           tmin           precip         nevada 
 Min.   :2.0   Min.   :-4.0   Min.   :-51.0   Min.   :19.0   Min.   :0  
 1st Qu.:2.0   1st Qu.: 0.0   1st Qu.:-48.0   1st Qu.:33.0   1st Qu.:0  
 Median :3.0   Median :35.0   Median :-26.0   Median :49.0   Median :0  
 Mean   :2.6   Mean   :20.6   Mean   :-32.8   Mean   :41.4   Mean   :0  
 3rd Qu.:3.0   3rd Qu.:36.0   3rd Qu.:-23.0   3rd Qu.:50.0   3rd Qu.:0  
 Max.   :3.0   Max.   :36.0   Max.   :-16.0   Max.   :56.0   Max.   :0  
   prof_nieve      longitud        latitud         altitud    
 Min.   :1017   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:1073   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :1168   Median :40.78   Median :-4.01   Median :1894  
 Mean   :1317   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:1494   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :1834   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt      tmax            tmin        precip          nevada   
 Min.   :2   Min.   :71.00   Min.   :-1   Min.   :14.00   Min.   :4.0  
 1st Qu.:2   1st Qu.:72.25   1st Qu.:-1   1st Qu.:15.25   1st Qu.:4.5  
 Median :2   Median :73.50   Median :-1   Median :16.50   Median :5.0  
 Mean   :2   Mean   :73.50   Mean   :-1   Mean   :16.50   Mean   :5.0  
 3rd Qu.:2   3rd Qu.:74.75   3rd Qu.:-1   3rd Qu.:17.75   3rd Qu.:5.5  
 Max.   :2   Max.   :76.00   Max.   :-1   Max.   :19.00   Max.   :6.0  
   prof_nieve    longitud        latitud          altitud     
 Min.   : 5   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.: 7   1st Qu.:40.78   1st Qu.:-2.846   1st Qu.:349.3  
 Median : 9   Median :41.08   Median :-2.242   Median :435.6  
 Mean   : 9   Mean   :41.08   Mean   :-2.242   Mean   :435.6  
 3rd Qu.:11   3rd Qu.:41.37   3rd Qu.:-1.637   3rd Qu.:521.8  
 Max.   :13   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip     
 Min.   : 1.000   Min.   : 69.0   Min.   :-15.00   Min.   : 3.00  
 1st Qu.: 2.000   1st Qu.: 89.0   1st Qu.: -5.00   1st Qu.: 7.50  
 Median : 2.000   Median : 96.0   Median : 27.00   Median :12.00  
 Mean   : 6.143   Mean   :100.4   Mean   : 14.29   Mean   :11.86  
 3rd Qu.:12.000   3rd Qu.:110.0   3rd Qu.: 31.50   3rd Qu.:14.50  
 Max.   :12.000   Max.   :140.0   Max.   : 35.00   Max.   :24.00  
     nevada        prof_nieve       longitud        latitud      
 Min.   :2.000   Min.   :0.000   Min.   :40.48   Min.   :-3.450  
 1st Qu.:2.000   1st Qu.:0.000   1st Qu.:40.48   1st Qu.:-3.450  
 Median :2.000   Median :1.000   Median :41.67   Median :-1.033  
 Mean   :2.143   Mean   :1.429   Mean   :41.16   Mean   :-2.069  
 3rd Qu.:2.000   3rd Qu.:1.000   3rd Qu.:41.67   3rd Qu.:-1.033  
 Max.   :3.000   Max.   :7.000   Max.   :41.67   Max.   :-1.033  
    altitud     
 Min.   :263.0  
 1st Qu.:263.0  
 Median :263.0  
 Mean   :410.9  
 3rd Qu.:608.1  
 Max.   :608.1  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.:148.0   1st Qu.:  53.00   1st Qu.:  3.00  
 Median : 6.000   Median :198.0   Median :  98.00   Median : 10.00  
 Mean   : 6.497   Mean   :200.2   Mean   :  98.87   Mean   : 16.25  
 3rd Qu.: 9.000   3rd Qu.:255.0   3rd Qu.: 148.00   3rd Qu.: 22.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :422.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.00e+00   Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.00e+00   1st Qu.:  0.0000   1st Qu.:38.28   1st Qu.: -5.6417  
 Median :0.00e+00   Median :  0.0000   Median :40.82   Median : -3.4500  
 Mean   :3.16e-05   Mean   :  0.3973   Mean   :39.66   Mean   : -3.4351  
 3rd Qu.:0.00e+00   3rd Qu.:  0.0000   3rd Qu.:42.08   3rd Qu.:  0.4914  
 Max.   :1.00e+00   Max.   :892.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  42.0  
 Median : 247.0  
 Mean   : 418.5  
 3rd Qu.: 656.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt        tmax           tmin           precip         nevada 
 Min.   :2.0   Min.   :-4.0   Min.   :-51.0   Min.   :19.0   Min.   :0  
 1st Qu.:2.0   1st Qu.: 0.0   1st Qu.:-48.0   1st Qu.:33.0   1st Qu.:0  
 Median :3.0   Median :35.0   Median :-26.0   Median :49.0   Median :0  
 Mean   :2.6   Mean   :20.6   Mean   :-32.8   Mean   :41.4   Mean   :0  
 3rd Qu.:3.0   3rd Qu.:36.0   3rd Qu.:-23.0   3rd Qu.:50.0   3rd Qu.:0  
 Max.   :3.0   Max.   :36.0   Max.   :-16.0   Max.   :56.0   Max.   :0  
   prof_nieve      longitud        latitud         altitud    
 Min.   :1017   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:1073   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :1168   Median :40.78   Median :-4.01   Median :1894  
 Mean   :1317   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:1494   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :1834   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt      tmax            tmin        precip          nevada   
 Min.   :2   Min.   :71.00   Min.   :-1   Min.   :14.00   Min.   :4.0  
 1st Qu.:2   1st Qu.:72.25   1st Qu.:-1   1st Qu.:15.25   1st Qu.:4.5  
 Median :2   Median :73.50   Median :-1   Median :16.50   Median :5.0  
 Mean   :2   Mean   :73.50   Mean   :-1   Mean   :16.50   Mean   :5.0  
 3rd Qu.:2   3rd Qu.:74.75   3rd Qu.:-1   3rd Qu.:17.75   3rd Qu.:5.5  
 Max.   :2   Max.   :76.00   Max.   :-1   Max.   :19.00   Max.   :6.0  
   prof_nieve    longitud        latitud          altitud     
 Min.   : 5   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.: 7   1st Qu.:40.78   1st Qu.:-2.846   1st Qu.:349.3  
 Median : 9   Median :41.08   Median :-2.242   Median :435.6  
 Mean   : 9   Mean   :41.08   Mean   :-2.242   Mean   :435.6  
 3rd Qu.:11   3rd Qu.:41.37   3rd Qu.:-1.637   3rd Qu.:521.8  
 Max.   :13   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip     
 Min.   : 1.000   Min.   : 69.0   Min.   :-15.00   Min.   : 3.00  
 1st Qu.: 2.000   1st Qu.: 89.0   1st Qu.: -5.00   1st Qu.: 7.50  
 Median : 2.000   Median : 96.0   Median : 27.00   Median :12.00  
 Mean   : 6.143   Mean   :100.4   Mean   : 14.29   Mean   :11.86  
 3rd Qu.:12.000   3rd Qu.:110.0   3rd Qu.: 31.50   3rd Qu.:14.50  
 Max.   :12.000   Max.   :140.0   Max.   : 35.00   Max.   :24.00  
     nevada        prof_nieve       longitud        latitud      
 Min.   :2.000   Min.   :0.000   Min.   :40.48   Min.   :-3.450  
 1st Qu.:2.000   1st Qu.:0.000   1st Qu.:40.48   1st Qu.:-3.450  
 Median :2.000   Median :1.000   Median :41.67   Median :-1.033  
 Mean   :2.143   Mean   :1.429   Mean   :41.16   Mean   :-2.069  
 3rd Qu.:2.000   3rd Qu.:1.000   3rd Qu.:41.67   3rd Qu.:-1.033  
 Max.   :3.000   Max.   :7.000   Max.   :41.67   Max.   :-1.033  
    altitud     
 Min.   :263.0  
 1st Qu.:263.0  
 Median :263.0  
 Mean   :410.9  
 3rd Qu.:608.1  
 Max.   :608.1  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.0   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.:148.2   1st Qu.:  53.0   1st Qu.:  3.00  
 Median : 6.000   Median :198.0   Median :  98.0   Median : 10.00  
 Mean   : 6.498   Mean   :200.3   Mean   :  98.9   Mean   : 16.24  
 3rd Qu.: 9.000   3rd Qu.:255.0   3rd Qu.: 148.0   3rd Qu.: 22.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.0   Max.   :422.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.00e+00   Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.00e+00   1st Qu.:  0.0000   1st Qu.:38.28   1st Qu.: -5.6417  
 Median :0.00e+00   Median :  0.0000   Median :40.82   Median : -3.4500  
 Mean   :3.16e-05   Mean   :  0.2657   Mean   :39.66   Mean   : -3.4350  
 3rd Qu.:0.00e+00   3rd Qu.:  0.0000   3rd Qu.:42.08   3rd Qu.:  0.4914  
 Max.   :1.00e+00   Max.   :390.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  42.0  
 Median : 247.0  
 Mean   : 418.1  
 3rd Qu.: 656.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin            precip           nevada 
 Min.   :1.000   Min.   :-12.00   Min.   :-72.00   Min.   : 16.00   Min.   :0  
 1st Qu.:2.000   1st Qu.: 10.00   1st Qu.:-44.00   1st Qu.: 36.00   1st Qu.:0  
 Median :2.000   Median : 15.00   Median :-34.00   Median : 52.00   Median :0  
 Mean   :2.333   Mean   : 24.19   Mean   :-31.95   Mean   : 61.29   Mean   :0  
 3rd Qu.:3.000   3rd Qu.: 29.00   3rd Qu.:-24.00   3rd Qu.: 78.00   3rd Qu.:0  
 Max.   :4.000   Max.   : 76.00   Max.   :  8.00   Max.   :180.00   Max.   :0  
   prof_nieve       longitud        latitud         altitud    
 Min.   :415.0   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:503.0   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :592.0   Median :40.78   Median :-4.01   Median :1894  
 Mean   :594.6   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:657.0   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :892.0   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt        tmax           tmin           precip         nevada 
 Min.   :2.0   Min.   :-4.0   Min.   :-51.0   Min.   :19.0   Min.   :0  
 1st Qu.:2.0   1st Qu.: 0.0   1st Qu.:-48.0   1st Qu.:33.0   1st Qu.:0  
 Median :3.0   Median :35.0   Median :-26.0   Median :49.0   Median :0  
 Mean   :2.6   Mean   :20.6   Mean   :-32.8   Mean   :41.4   Mean   :0  
 3rd Qu.:3.0   3rd Qu.:36.0   3rd Qu.:-23.0   3rd Qu.:50.0   3rd Qu.:0  
 Max.   :3.0   Max.   :36.0   Max.   :-16.0   Max.   :56.0   Max.   :0  
   prof_nieve      longitud        latitud         altitud    
 Min.   :1017   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:1073   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :1168   Median :40.78   Median :-4.01   Median :1894  
 Mean   :1317   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:1494   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :1834   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt      tmax            tmin        precip          nevada   
 Min.   :2   Min.   :71.00   Min.   :-1   Min.   :14.00   Min.   :4.0  
 1st Qu.:2   1st Qu.:72.25   1st Qu.:-1   1st Qu.:15.25   1st Qu.:4.5  
 Median :2   Median :73.50   Median :-1   Median :16.50   Median :5.0  
 Mean   :2   Mean   :73.50   Mean   :-1   Mean   :16.50   Mean   :5.0  
 3rd Qu.:2   3rd Qu.:74.75   3rd Qu.:-1   3rd Qu.:17.75   3rd Qu.:5.5  
 Max.   :2   Max.   :76.00   Max.   :-1   Max.   :19.00   Max.   :6.0  
   prof_nieve    longitud        latitud          altitud     
 Min.   : 5   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.: 7   1st Qu.:40.78   1st Qu.:-2.846   1st Qu.:349.3  
 Median : 9   Median :41.08   Median :-2.242   Median :435.6  
 Mean   : 9   Mean   :41.08   Mean   :-2.242   Mean   :435.6  
 3rd Qu.:11   3rd Qu.:41.37   3rd Qu.:-1.637   3rd Qu.:521.8  
 Max.   :13   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip     
 Min.   : 1.000   Min.   : 69.0   Min.   :-15.00   Min.   : 3.00  
 1st Qu.: 2.000   1st Qu.: 89.0   1st Qu.: -5.00   1st Qu.: 7.50  
 Median : 2.000   Median : 96.0   Median : 27.00   Median :12.00  
 Mean   : 6.143   Mean   :100.4   Mean   : 14.29   Mean   :11.86  
 3rd Qu.:12.000   3rd Qu.:110.0   3rd Qu.: 31.50   3rd Qu.:14.50  
 Max.   :12.000   Max.   :140.0   Max.   : 35.00   Max.   :24.00  
     nevada        prof_nieve       longitud        latitud      
 Min.   :2.000   Min.   :0.000   Min.   :40.48   Min.   :-3.450  
 1st Qu.:2.000   1st Qu.:0.000   1st Qu.:40.48   1st Qu.:-3.450  
 Median :2.000   Median :1.000   Median :41.67   Median :-1.033  
 Mean   :2.143   Mean   :1.429   Mean   :41.16   Mean   :-2.069  
 3rd Qu.:2.000   3rd Qu.:1.000   3rd Qu.:41.67   3rd Qu.:-1.033  
 Max.   :3.000   Max.   :7.000   Max.   :41.67   Max.   :-1.033  
    altitud     
 Min.   :263.0  
 1st Qu.:263.0  
 Median :263.0  
 Mean   :410.9  
 3rd Qu.:608.1  
 Max.   :608.1  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   :86.00   Min.   :-24.0   Min.   : 6.00   Min.   :1  
 1st Qu.: 6.500   1st Qu.:86.00   1st Qu.:-19.5   1st Qu.: 6.00   1st Qu.:1  
 Median :12.000   Median :86.00   Median :-15.0   Median : 6.00   Median :1  
 Mean   : 8.333   Mean   :88.33   Mean   : -7.0   Mean   :10.33   Mean   :1  
 3rd Qu.:12.000   3rd Qu.:89.50   3rd Qu.:  1.5   3rd Qu.:12.50   3rd Qu.:1  
 Max.   :12.000   Max.   :93.00   Max.   : 18.0   Max.   :19.00   Max.   :1  
   prof_nieve        longitud        latitud          altitud     
 Min.   :0.0000   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.:0.0000   1st Qu.:40.48   1st Qu.:-3.450   1st Qu.:435.6  
 Median :0.0000   Median :40.48   Median :-3.450   Median :608.1  
 Mean   :0.3333   Mean   :40.88   Mean   :-2.644   Mean   :493.1  
 3rd Qu.:0.5000   3rd Qu.:41.08   3rd Qu.:-2.242   3rd Qu.:608.1  
 Max.   :1.0000   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:149.0   1st Qu.:  53.0   1st Qu.:  3.00   1st Qu.:0  
 Median : 6.000   Median :198.0   Median :  98.0   Median : 10.00   Median :0  
 Mean   : 6.498   Mean   :200.3   Mean   :  98.9   Mean   : 16.24   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:255.0   3rd Qu.: 148.0   3rd Qu.: 22.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   : 254.0   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :  0.0000   Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :  0.2657   Mean   :39.66   Mean   : -3.4350   Mean   : 418.1  
 3rd Qu.:  0.0000   3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :390.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax             tmin            precip           nevada 
 Min.   :1.000   Min.   :-12.00   Min.   :-72.00   Min.   : 16.00   Min.   :0  
 1st Qu.:2.000   1st Qu.: 10.00   1st Qu.:-44.00   1st Qu.: 36.00   1st Qu.:0  
 Median :2.000   Median : 15.00   Median :-34.00   Median : 52.00   Median :0  
 Mean   :2.333   Mean   : 24.19   Mean   :-31.95   Mean   : 61.29   Mean   :0  
 3rd Qu.:3.000   3rd Qu.: 29.00   3rd Qu.:-24.00   3rd Qu.: 78.00   3rd Qu.:0  
 Max.   :4.000   Max.   : 76.00   Max.   :  8.00   Max.   :180.00   Max.   :0  
   prof_nieve       longitud        latitud         altitud    
 Min.   :415.0   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:503.0   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :592.0   Median :40.78   Median :-4.01   Median :1894  
 Mean   :594.6   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:657.0   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :892.0   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt        tmax           tmin           precip         nevada 
 Min.   :2.0   Min.   :-4.0   Min.   :-51.0   Min.   :19.0   Min.   :0  
 1st Qu.:2.0   1st Qu.: 0.0   1st Qu.:-48.0   1st Qu.:33.0   1st Qu.:0  
 Median :3.0   Median :35.0   Median :-26.0   Median :49.0   Median :0  
 Mean   :2.6   Mean   :20.6   Mean   :-32.8   Mean   :41.4   Mean   :0  
 3rd Qu.:3.0   3rd Qu.:36.0   3rd Qu.:-23.0   3rd Qu.:50.0   3rd Qu.:0  
 Max.   :3.0   Max.   :36.0   Max.   :-16.0   Max.   :56.0   Max.   :0  
   prof_nieve      longitud        latitud         altitud    
 Min.   :1017   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:1073   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :1168   Median :40.78   Median :-4.01   Median :1894  
 Mean   :1317   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:1494   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :1834   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt      tmax            tmin        precip          nevada   
 Min.   :2   Min.   :71.00   Min.   :-1   Min.   :14.00   Min.   :4.0  
 1st Qu.:2   1st Qu.:72.25   1st Qu.:-1   1st Qu.:15.25   1st Qu.:4.5  
 Median :2   Median :73.50   Median :-1   Median :16.50   Median :5.0  
 Mean   :2   Mean   :73.50   Mean   :-1   Mean   :16.50   Mean   :5.0  
 3rd Qu.:2   3rd Qu.:74.75   3rd Qu.:-1   3rd Qu.:17.75   3rd Qu.:5.5  
 Max.   :2   Max.   :76.00   Max.   :-1   Max.   :19.00   Max.   :6.0  
   prof_nieve    longitud        latitud          altitud     
 Min.   : 5   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.: 7   1st Qu.:40.78   1st Qu.:-2.846   1st Qu.:349.3  
 Median : 9   Median :41.08   Median :-2.242   Median :435.6  
 Mean   : 9   Mean   :41.08   Mean   :-2.242   Mean   :435.6  
 3rd Qu.:11   3rd Qu.:41.37   3rd Qu.:-1.637   3rd Qu.:521.8  
 Max.   :13   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip     
 Min.   : 1.000   Min.   : 69.0   Min.   :-15.00   Min.   : 3.00  
 1st Qu.: 2.000   1st Qu.: 89.0   1st Qu.: -5.00   1st Qu.: 7.50  
 Median : 2.000   Median : 96.0   Median : 27.00   Median :12.00  
 Mean   : 6.143   Mean   :100.4   Mean   : 14.29   Mean   :11.86  
 3rd Qu.:12.000   3rd Qu.:110.0   3rd Qu.: 31.50   3rd Qu.:14.50  
 Max.   :12.000   Max.   :140.0   Max.   : 35.00   Max.   :24.00  
     nevada        prof_nieve       longitud        latitud      
 Min.   :2.000   Min.   :0.000   Min.   :40.48   Min.   :-3.450  
 1st Qu.:2.000   1st Qu.:0.000   1st Qu.:40.48   1st Qu.:-3.450  
 Median :2.000   Median :1.000   Median :41.67   Median :-1.033  
 Mean   :2.143   Mean   :1.429   Mean   :41.16   Mean   :-2.069  
 3rd Qu.:2.000   3rd Qu.:1.000   3rd Qu.:41.67   3rd Qu.:-1.033  
 Max.   :3.000   Max.   :7.000   Max.   :41.67   Max.   :-1.033  
    altitud     
 Min.   :263.0  
 1st Qu.:263.0  
 Median :263.0  
 Mean   :410.9  
 3rd Qu.:608.1  
 Max.   :608.1  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   :86.00   Min.   :-24.0   Min.   : 6.00   Min.   :1  
 1st Qu.: 6.500   1st Qu.:86.00   1st Qu.:-19.5   1st Qu.: 6.00   1st Qu.:1  
 Median :12.000   Median :86.00   Median :-15.0   Median : 6.00   Median :1  
 Mean   : 8.333   Mean   :88.33   Mean   : -7.0   Mean   :10.33   Mean   :1  
 3rd Qu.:12.000   3rd Qu.:89.50   3rd Qu.:  1.5   3rd Qu.:12.50   3rd Qu.:1  
 Max.   :12.000   Max.   :93.00   Max.   : 18.0   Max.   :19.00   Max.   :1  
   prof_nieve        longitud        latitud          altitud     
 Min.   :0.0000   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.:0.0000   1st Qu.:40.48   1st Qu.:-3.450   1st Qu.:435.6  
 Median :0.0000   Median :40.48   Median :-3.450   Median :608.1  
 Mean   :0.3333   Mean   :40.88   Mean   :-2.644   Mean   :493.1  
 3rd Qu.:0.5000   3rd Qu.:41.08   3rd Qu.:-2.242   3rd Qu.:608.1  
 Max.   :1.0000   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.00   1st Qu.:150.0   1st Qu.:  52.00   1st Qu.:  2.00   1st Qu.:0  
 Median : 6.00   Median :201.0   Median :  99.00   Median :  9.00   Median :0  
 Mean   : 6.45   Mean   :202.3   Mean   :  99.41   Mean   : 12.89   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:258.0   3rd Qu.: 150.00   3rd Qu.: 20.00   3rd Qu.:0  
 Max.   :12.00   Max.   :403.0   Max.   : 254.00   Max.   :106.00   Max.   :0  
   prof_nieve           longitud        latitud            altitud      
 Min.   :  0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:38.00   1st Qu.: -5.6156   1st Qu.:  42.0  
 Median :  0.00000   Median :40.82   Median : -3.1642   Median : 251.0  
 Mean   :  0.09985   Mean   :39.57   Mean   : -3.3877   Mean   : 424.6  
 3rd Qu.:  0.00000   3rd Qu.:41.98   3rd Qu.:  0.4914   3rd Qu.: 667.0  
 Max.   :108.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin            precip      
 Min.   : 1.000   Min.   :-12.00   Min.   :-63.00   Min.   :  2.00  
 1st Qu.: 1.000   1st Qu.: 16.00   1st Qu.:-35.75   1st Qu.: 30.25  
 Median : 2.000   Median : 34.00   Median :-24.00   Median : 43.50  
 Mean   : 3.614   Mean   : 35.79   Mean   :-22.81   Mean   : 47.31  
 3rd Qu.: 4.000   3rd Qu.: 49.00   3rd Qu.: -8.25   3rd Qu.: 66.75  
 Max.   :12.000   Max.   : 99.00   Max.   : 28.00   Max.   :126.00  
     nevada    prof_nieve       longitud        latitud         altitud    
 Min.   :0   Min.   :114.0   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:0   1st Qu.:147.2   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :0   Median :200.5   Median :40.78   Median :-4.01   Median :1894  
 Mean   :0   Mean   :213.4   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:0   3rd Qu.:266.5   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :0   Max.   :390.0   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-42.0   Min.   :-102.00   Min.   : 38.00  
 1st Qu.: 3.000   1st Qu.:136.0   1st Qu.:  66.00   1st Qu.: 55.00  
 Median : 9.000   Median :166.0   Median :  92.00   Median : 65.00  
 Mean   : 7.353   Mean   :167.1   Mean   :  91.88   Mean   : 73.23  
 3rd Qu.:11.000   3rd Qu.:199.0   3rd Qu.: 120.00   3rd Qu.: 83.00  
 Max.   :12.000   Max.   :350.0   Max.   : 223.00   Max.   :422.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :  0.0000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:  0.0000   1st Qu.:40.78   1st Qu.: -8.372  
 Median :0   Median :  0.0000   Median :42.43   Median : -3.831  
 Mean   :0   Mean   :  0.2526   Mean   :41.17   Mean   : -4.238  
 3rd Qu.:0   3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -1.787  
 Max.   :0   Max.   :106.0000   Max.   :43.57   Max.   :  4.216  
    altitud    
 Min.   :   1  
 1st Qu.:  32  
 Median :  98  
 Mean   : 288  
 3rd Qu.: 359  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax             tmin            precip           nevada 
 Min.   :1.000   Min.   :-12.00   Min.   :-72.00   Min.   : 16.00   Min.   :0  
 1st Qu.:2.000   1st Qu.: 10.00   1st Qu.:-44.00   1st Qu.: 36.00   1st Qu.:0  
 Median :2.000   Median : 15.00   Median :-34.00   Median : 52.00   Median :0  
 Mean   :2.333   Mean   : 24.19   Mean   :-31.95   Mean   : 61.29   Mean   :0  
 3rd Qu.:3.000   3rd Qu.: 29.00   3rd Qu.:-24.00   3rd Qu.: 78.00   3rd Qu.:0  
 Max.   :4.000   Max.   : 76.00   Max.   :  8.00   Max.   :180.00   Max.   :0  
   prof_nieve       longitud        latitud         altitud    
 Min.   :415.0   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:503.0   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :592.0   Median :40.78   Median :-4.01   Median :1894  
 Mean   :594.6   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:657.0   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :892.0   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt        tmax           tmin           precip         nevada 
 Min.   :2.0   Min.   :-4.0   Min.   :-51.0   Min.   :19.0   Min.   :0  
 1st Qu.:2.0   1st Qu.: 0.0   1st Qu.:-48.0   1st Qu.:33.0   1st Qu.:0  
 Median :3.0   Median :35.0   Median :-26.0   Median :49.0   Median :0  
 Mean   :2.6   Mean   :20.6   Mean   :-32.8   Mean   :41.4   Mean   :0  
 3rd Qu.:3.0   3rd Qu.:36.0   3rd Qu.:-23.0   3rd Qu.:50.0   3rd Qu.:0  
 Max.   :3.0   Max.   :36.0   Max.   :-16.0   Max.   :56.0   Max.   :0  
   prof_nieve      longitud        latitud         altitud    
 Min.   :1017   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:1073   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :1168   Median :40.78   Median :-4.01   Median :1894  
 Mean   :1317   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:1494   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :1834   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt      tmax            tmin        precip          nevada   
 Min.   :2   Min.   :71.00   Min.   :-1   Min.   :14.00   Min.   :4.0  
 1st Qu.:2   1st Qu.:72.25   1st Qu.:-1   1st Qu.:15.25   1st Qu.:4.5  
 Median :2   Median :73.50   Median :-1   Median :16.50   Median :5.0  
 Mean   :2   Mean   :73.50   Mean   :-1   Mean   :16.50   Mean   :5.0  
 3rd Qu.:2   3rd Qu.:74.75   3rd Qu.:-1   3rd Qu.:17.75   3rd Qu.:5.5  
 Max.   :2   Max.   :76.00   Max.   :-1   Max.   :19.00   Max.   :6.0  
   prof_nieve    longitud        latitud          altitud     
 Min.   : 5   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.: 7   1st Qu.:40.78   1st Qu.:-2.846   1st Qu.:349.3  
 Median : 9   Median :41.08   Median :-2.242   Median :435.6  
 Mean   : 9   Mean   :41.08   Mean   :-2.242   Mean   :435.6  
 3rd Qu.:11   3rd Qu.:41.37   3rd Qu.:-1.637   3rd Qu.:521.8  
 Max.   :13   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip     
 Min.   : 1.000   Min.   : 69.0   Min.   :-15.00   Min.   : 3.00  
 1st Qu.: 2.000   1st Qu.: 89.0   1st Qu.: -5.00   1st Qu.: 7.50  
 Median : 2.000   Median : 96.0   Median : 27.00   Median :12.00  
 Mean   : 6.143   Mean   :100.4   Mean   : 14.29   Mean   :11.86  
 3rd Qu.:12.000   3rd Qu.:110.0   3rd Qu.: 31.50   3rd Qu.:14.50  
 Max.   :12.000   Max.   :140.0   Max.   : 35.00   Max.   :24.00  
     nevada        prof_nieve       longitud        latitud      
 Min.   :2.000   Min.   :0.000   Min.   :40.48   Min.   :-3.450  
 1st Qu.:2.000   1st Qu.:0.000   1st Qu.:40.48   1st Qu.:-3.450  
 Median :2.000   Median :1.000   Median :41.67   Median :-1.033  
 Mean   :2.143   Mean   :1.429   Mean   :41.16   Mean   :-2.069  
 3rd Qu.:2.000   3rd Qu.:1.000   3rd Qu.:41.67   3rd Qu.:-1.033  
 Max.   :3.000   Max.   :7.000   Max.   :41.67   Max.   :-1.033  
    altitud     
 Min.   :263.0  
 1st Qu.:263.0  
 Median :263.0  
 Mean   :410.9  
 3rd Qu.:608.1  
 Max.   :608.1  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   :86.00   Min.   :-24.0   Min.   : 6.00   Min.   :1  
 1st Qu.: 6.500   1st Qu.:86.00   1st Qu.:-19.5   1st Qu.: 6.00   1st Qu.:1  
 Median :12.000   Median :86.00   Median :-15.0   Median : 6.00   Median :1  
 Mean   : 8.333   Mean   :88.33   Mean   : -7.0   Mean   :10.33   Mean   :1  
 3rd Qu.:12.000   3rd Qu.:89.50   3rd Qu.:  1.5   3rd Qu.:12.50   3rd Qu.:1  
 Max.   :12.000   Max.   :93.00   Max.   : 18.0   Max.   :19.00   Max.   :1  
   prof_nieve        longitud        latitud          altitud     
 Min.   :0.0000   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.:0.0000   1st Qu.:40.48   1st Qu.:-3.450   1st Qu.:435.6  
 Median :0.0000   Median :40.48   Median :-3.450   Median :608.1  
 Mean   :0.3333   Mean   :40.88   Mean   :-2.644   Mean   :493.1  
 3rd Qu.:0.5000   3rd Qu.:41.08   3rd Qu.:-2.242   3rd Qu.:608.1  
 Max.   :1.0000   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:129.0   1st Qu.:  28.00   1st Qu.:  5.00   1st Qu.:0  
 Median :3.000   Median :162.0   Median :  61.00   Median : 13.00   Median :0  
 Mean   :2.956   Mean   :157.1   Mean   :  58.32   Mean   : 15.84   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:191.0   3rd Qu.:  89.00   3rd Qu.: 24.00   3rd Qu.:0  
 Max.   :7.000   Max.   :281.0   Max.   : 185.00   Max.   :106.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:38.95   1st Qu.: -5.5975   1st Qu.:  47.0  
 Median :  0.0000   Median :40.95   Median : -2.9553   Median : 353.0  
 Mean   :  0.1626   Mean   :39.99   Mean   : -3.1413   Mean   : 476.4  
 3rd Qu.:  0.0000   3rd Qu.:42.18   3rd Qu.:  0.4914   3rd Qu.: 704.0  
 Max.   :108.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   :172.0   Min.   : 67.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 6.000   1st Qu.:243.0   1st Qu.:135.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.000   Median :270.0   Median :158.0   Median : 4.000   Median :0  
 Mean   : 7.527   Mean   :271.7   Mean   :159.4   Mean   : 7.838   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:297.0   3rd Qu.:183.0   3rd Qu.:12.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :58.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8792   1st Qu.:  32.0  
 Median : 0.00000   Median :40.07   Median : -3.6325   Median :  91.0  
 Mean   : 0.00243   Mean   :38.74   Mean   : -3.9588   Mean   : 301.5  
 3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.:  0.4731   3rd Qu.: 554.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax             tmin            precip      
 Min.   : 1.000   Min.   :-12.00   Min.   :-63.00   Min.   :  2.00  
 1st Qu.: 1.000   1st Qu.: 16.00   1st Qu.:-35.75   1st Qu.: 30.25  
 Median : 2.000   Median : 34.00   Median :-24.00   Median : 43.50  
 Mean   : 3.614   Mean   : 35.79   Mean   :-22.81   Mean   : 47.31  
 3rd Qu.: 4.000   3rd Qu.: 49.00   3rd Qu.: -8.25   3rd Qu.: 66.75  
 Max.   :12.000   Max.   : 99.00   Max.   : 28.00   Max.   :126.00  
     nevada    prof_nieve       longitud        latitud         altitud    
 Min.   :0   Min.   :114.0   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:0   1st Qu.:147.2   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :0   Median :200.5   Median :40.78   Median :-4.01   Median :1894  
 Mean   :0   Mean   :213.4   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:0   3rd Qu.:266.5   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :0   Max.   :390.0   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-42.0   Min.   :-102.00   Min.   : 38.00  
 1st Qu.: 3.000   1st Qu.:136.0   1st Qu.:  66.00   1st Qu.: 55.00  
 Median : 9.000   Median :166.0   Median :  92.00   Median : 65.00  
 Mean   : 7.353   Mean   :167.1   Mean   :  91.88   Mean   : 73.23  
 3rd Qu.:11.000   3rd Qu.:199.0   3rd Qu.: 120.00   3rd Qu.: 83.00  
 Max.   :12.000   Max.   :350.0   Max.   : 223.00   Max.   :422.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :  0.0000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:  0.0000   1st Qu.:40.78   1st Qu.: -8.372  
 Median :0   Median :  0.0000   Median :42.43   Median : -3.831  
 Mean   :0   Mean   :  0.2526   Mean   :41.17   Mean   : -4.238  
 3rd Qu.:0   3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -1.787  
 Max.   :0   Max.   :106.0000   Max.   :43.57   Max.   :  4.216  
    altitud    
 Min.   :   1  
 1st Qu.:  32  
 Median :  98  
 Mean   : 288  
 3rd Qu.: 359  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax             tmin            precip           nevada 
 Min.   :1.000   Min.   :-12.00   Min.   :-72.00   Min.   : 16.00   Min.   :0  
 1st Qu.:2.000   1st Qu.: 10.00   1st Qu.:-44.00   1st Qu.: 36.00   1st Qu.:0  
 Median :2.000   Median : 15.00   Median :-34.00   Median : 52.00   Median :0  
 Mean   :2.333   Mean   : 24.19   Mean   :-31.95   Mean   : 61.29   Mean   :0  
 3rd Qu.:3.000   3rd Qu.: 29.00   3rd Qu.:-24.00   3rd Qu.: 78.00   3rd Qu.:0  
 Max.   :4.000   Max.   : 76.00   Max.   :  8.00   Max.   :180.00   Max.   :0  
   prof_nieve       longitud        latitud         altitud    
 Min.   :415.0   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:503.0   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :592.0   Median :40.78   Median :-4.01   Median :1894  
 Mean   :594.6   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:657.0   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :892.0   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin             precip          nevada 
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:117.0   1st Qu.:  30.00   1st Qu.: 6.00   1st Qu.:0  
 Median :11.00   Median :152.0   Median :  60.00   Median :14.00   Median :0  
 Mean   :11.06   Mean   :148.7   Mean   :  57.06   Mean   :17.44   Mean   :0  
 3rd Qu.:12.00   3rd Qu.:184.0   3rd Qu.:  87.00   3rd Qu.:26.00   3rd Qu.:0  
 Max.   :12.00   Max.   :265.0   Max.   : 165.00   Max.   :88.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -4.8458   1st Qu.:  81.0  
 Median :  0.0000   Median :41.11   Median : -2.4831   Median : 513.0  
 Mean   :  0.1765   Mean   :40.46   Mean   : -2.7019   Mean   : 574.8  
 3rd Qu.:  0.0000   3rd Qu.:42.24   3rd Qu.:  0.5706   3rd Qu.: 790.0  
 Max.   :108.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt        tmax           tmin           precip         nevada 
 Min.   :2.0   Min.   :-4.0   Min.   :-51.0   Min.   :19.0   Min.   :0  
 1st Qu.:2.0   1st Qu.: 0.0   1st Qu.:-48.0   1st Qu.:33.0   1st Qu.:0  
 Median :3.0   Median :35.0   Median :-26.0   Median :49.0   Median :0  
 Mean   :2.6   Mean   :20.6   Mean   :-32.8   Mean   :41.4   Mean   :0  
 3rd Qu.:3.0   3rd Qu.:36.0   3rd Qu.:-23.0   3rd Qu.:50.0   3rd Qu.:0  
 Max.   :3.0   Max.   :36.0   Max.   :-16.0   Max.   :56.0   Max.   :0  
   prof_nieve      longitud        latitud         altitud    
 Min.   :1017   Min.   :40.78   Min.   :-4.01   Min.   :1894  
 1st Qu.:1073   1st Qu.:40.78   1st Qu.:-4.01   1st Qu.:1894  
 Median :1168   Median :40.78   Median :-4.01   Median :1894  
 Mean   :1317   Mean   :40.78   Mean   :-4.01   Mean   :1894  
 3rd Qu.:1494   3rd Qu.:40.78   3rd Qu.:-4.01   3rd Qu.:1894  
 Max.   :1834   Max.   :40.78   Max.   :-4.01   Max.   :1894  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt      tmax            tmin        precip          nevada   
 Min.   :2   Min.   :71.00   Min.   :-1   Min.   :14.00   Min.   :4.0  
 1st Qu.:2   1st Qu.:72.25   1st Qu.:-1   1st Qu.:15.25   1st Qu.:4.5  
 Median :2   Median :73.50   Median :-1   Median :16.50   Median :5.0  
 Mean   :2   Mean   :73.50   Mean   :-1   Mean   :16.50   Mean   :5.0  
 3rd Qu.:2   3rd Qu.:74.75   3rd Qu.:-1   3rd Qu.:17.75   3rd Qu.:5.5  
 Max.   :2   Max.   :76.00   Max.   :-1   Max.   :19.00   Max.   :6.0  
   prof_nieve    longitud        latitud          altitud     
 Min.   : 5   Min.   :40.48   Min.   :-3.450   Min.   :263.0  
 1st Qu.: 7   1st Qu.:40.78   1st Qu.:-2.846   1st Qu.:349.3  
 Median : 9   Median :41.08   Median :-2.242   Median :435.6  
 Mean   : 9   Mean   :41.08   Mean   :-2.242   Mean   :435.6  
 3rd Qu.:11   3rd Qu.:41.37   3rd Qu.:-1.637   3rd Qu.:521.8  
 Max.   :13   Max.   :41.67   Max.   :-1.033   Max.   :608.1  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)